koptimizer / my_PaperLog

심심할때 논문 읽고 리뷰하는 공간
1 stars 0 forks source link

Human-level control through deep reinforcement learning #5

Closed koptimizer closed 4 years ago

koptimizer commented 4 years ago

:clipboard: 논문의 정보를 알려주세요.

:page_with_curl: Abstract(본문)

The theory of reinforcement learning provides a normative account1, deeply rooted in psychological2 and neuroscientific3 perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems4,5, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms3. While reinforcement learning agents have achieved some successes in a variety of domains6,7,8, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks9,10,11 to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games12. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

:mag_right: 어떤 논문인지 소개해주세요.

:key: 핵심 키워드를 적어주세요.

Action-value(Q) function, DQN, CNN

:paperclip: URL

https://www.nature.com/articles/nature14236.

koptimizer commented 4 years ago

:bulb: 방법은 무엇입니까?

:chart_with_upwards_trend: 실험과 그 결과는 어떻습니까?

:open_file_folder: 차후 연구방향 및 보완점은 무엇입니까?

:thumbsup: novelty와 논문을 통해 배운 것은 무엇입니까?

:loop: 궁금한 점이나 추가로 읽으면 좋은 레퍼런스가 있습니까?